通过动态选择对比层，有效减少大模型生成中的幻觉问题。
Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation
- 将解码过程建模为决策问题，按需激活对比层
- 在五个基准上优于现有方法，显著降低幻觉率
- 适合追求高事实性、长文本生成的场景
近期的解码方法通过优化生成过程中下一个词元的选择来提升大语言模型（LLMs）的事实性。这些方法通常在词元层面操作，利用内部表征抑制表面模式。然而，大模型在长上下文下仍易产生幻觉。本文提出主动层对比解码（ActLCD），一种新型解码策略，可主动决定何时应用对比层。通过将解码视为序列决策问题，ActLCD采用由奖励感知分类器引导的强化学习策略，在词元层面之外优化事实性。实验表明，ActLCD在五个基准测试中均超越现有最佳方法，证明其在多种生成场景中有效缓解幻觉。
原文摘要 · Abstract (English)
Recent decoding methods improve the factuality of large language models (LLMs) by refining how the next token is selected during generation. These methods typically operate at the token level, leveraging internal representations to suppress superficial patterns. Nevertheless, LLMs remain prone to hallucinations, especially over longer contexts. In this paper, we propose Active Layer-Contrastive Decoding (ActLCD), a novel decoding strategy that actively decides when to apply contrasting layers during generation. By casting decoding as a sequential decision-making problem, ActLCD employs a reinforcement learning policy guided by a reward-aware classifier to optimize factuality beyond the token level. Our experiments demonstrate that ActLCD surpasses state-of-the-art methods across five benchmarks, showcasing its effectiveness in mitigating hallucinations in diverse generation scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。